Hi HN — I built this because most AI app builders frustrated me.
They’re usually cloud-only, expensive, and generate code that looks good in demos but breaks or hallucinates when you try to extend it. I wanted something I could actually use for real projects.
So I built a local-first full-stack generator that runs inside VS Code and writes files directly to your machine.
It can scaffold:
frontend (React/Next/etc)
backend APIs
database models
basic auth/CRUD flows
The focus is reliability over “magic”. I try to keep generation constrained and file-aware to reduce hallucinations and produce clean, editable code.
Cost is ~$0.5–$1 per project using small models, so it’s cheap enough to use daily.
Still early, but I’m already using it to ship internal tools and small client apps.
Would genuinely love feedback from other devs — especially where it breaks or feels unreliable.
I built a local-first AI full-stack code generator that creates complete web and mobile apps from prompts.
Most AI app builders run everything in the cloud, are expensive, and often hallucinate or generate messy code that’s hard to edit. I wanted something cheaper, private, and more predictable.
So this tool:
runs locally in VS Code
saves all files directly on your machine (no remote servers)
generates frontend + backend + database together
produces editable, production-style code (not locked templates)
costs ~free for now per project using small/efficient models
focuses on reducing hallucinations with constrained generation + file-aware context
You can scaffold things like:
CRUD dashboards
SaaS apps
landing pages
REST APIs
full-stack MVPs
The goal isn’t “magic one-click apps”, but practical, reliable code you can actually maintain.
Still early, but already using it to ship internal tools and small client projects.
Would love feedback from other devs — especially on reliability and workflows.
Just to clarify, this is still early.
Our goal is not to replace designers or developers, but to handle the initial 70–80% of UI boilerplate so teams can focus on logic and UX polish.
Hi HN,
We’ve just launched Elaric AI Beta, a tool that generates complete mobile app UI in clean HTML/CSS from natural language prompts.
Most tools generate fragments or components.
Elaric tries to generate full multi-screen UI flows, including:
Mobile-first responsive layouts
Clean, readable HTML/CSS (no unnecessary frameworks)
Component-level CSS (no inline clutter)
Navigation + multi-page structure
Light/dark UI variants
Edit-anything mode
Export options
Our goal is to help developers go from idea → working UI in minutes, without writing boilerplate.
We are a small team from Nepal, and this is our first public beta.
We know there will be rough edges, and we’d appreciate feedback from this community — especially around UI structure, code quality, and prompts.
Happy to answer any questions about how it works.
Right now it only generates mobile app UI screens (no full app logic yet), so we’re trying to understand what direction would be most useful for builders here.
Open to any feedback.
We’re two founders from Nepal building a tool that auto-generates mobile app UI screens.
It’s very early — only UI works for now.
Would love to hear what HN thinks we should build next.
Thanks everyone for checking this out! I’m here for the entire day and will respond to all feedback, questions, and criticism. Please feel free to be brutally honest — it really helps us improve.
Hi HN,
I'm Aman, a 20-year-old builder from Nepal, and for the last few months my co-founder (Alok) and I have been working on a small but meaningful experiment:
Can AI generate clean, usable mobile app UI screens instantly from a text prompt?
Today, we’re releasing the beta of Elaric, a tool that does exactly that.
What it does (current version)
Right now, Elaric generates UI screens only — but across almost all major categories:
Food delivery
E-commerce
Booking apps
Finance
Fitness
Education
Social
Hospitality
Ride-hailing
Marketplaces
You type:
“Generate a home page for a food delivery app with categories, a search bar, and a featured section.”
Elaric outputs a complete UI screen in seconds.
You can generate unlimited screens and explore them visually.
Why we built this
In Nepal, building an app UI takes days or weeks.
Figma is powerful, but for non-designers, it’s still overwhelming.
We wanted something simple:
“Describe the screen you want → get a usable mockup immediately.”
We know this is not new at a global level, but it is new in our context — and we wanted to see how far two young builders with almost no resources can push this idea.
How we built it
We bootstrapped the entire thing with ₹51,125.
No investors, no team, no external help.
We trained and fine-tuned models on a lot of manually prepared UI structures and category patterns, and then built a rendering engine that constructs the final screen layout.
It’s definitely not perfect — but it works surprisingly well for many categories.
Why we’re posting on HN
Because this community is where we’ve learned everything.
We respect the honesty here more than any other platform.
We want feedback on:
What would make this actually useful for developers/designers?
Should we prioritize code export or screen linking next?
Should the editor come before flow generation?
Any obvious limitations you see from the demo?
Any categories we should add next?
Live Beta:
https://www.elaric.ai/
(If it crashes, we’ll scale quickly — our servers are tiny.)
What’s next
Based on early user requests, our next steps are:
Add Figma export
Add screen-to-screen linking
Create a small built-in UI editor
Generate React Native code
Build full app flows
Release an API for bulk UI generation
Why this matters to us
We grew up in a place where people genuinely believe “big tech can’t be built in Nepal.”
Posting this here is a small step toward challenging that.
If anyone here finds this useful — even for 10 seconds — it will mean everything to us.
I’ll be here in the comments all day.
Thank you for your time, and happy to answer anything.
Aman
Co-founder, Elaric
https://www.elaric.ai/
reply